Comparing 2 models
DeepSeek V4.1 Flash vs Gemini 3.1 Pro Preview
Benchmarks through
Verdict
DeepSeek V4.1 Flash and Gemini 3.1 Pro Preview are not yet ranked on the same task, so compare the specifications below. DeepSeek V4.1 Flash costs 39.4x less per input token. Only DeepSeek V4.1 Flash has open weights for self-hosting.
- Choose DeepSeek V4.1 Flash for you need to self-host.
Built from the published task rankings below; ranks come from each task's own weighted benchmarks, so a win on one task says nothing about another.
Measured head to head
Benchmarks both models were run on
| Evaluation | DeepSeek V4.1 Flash | Gemini 3.1 Pro Preview | Source |
|---|---|---|---|
| FrontierMath Tiers 1-3 (Epoch AI) | 67.4% ± 2.8 | 59.6% ± 2.9 | source · 2026-10-08 |
| GPQA Diamond (Epoch AI) | 89.8% ± 1.7 | 94.1% ± 1.7 | source · 2026-10-09 |
| LiveBench Agentic Coding | 77.3% | 44.1% | source · 2026-10-18 |
| LiveBench Coding | 80.0% | 76.5% | source · 2026-10-18 |
| LiveBench Data Analysis | 79.3% | 78.5% | source · 2026-10-18 |
| LiveBench Instruction Following | 70.0% | 79.1% | source · 2026-10-18 |
| LiveBench Language | 81.2% | 85.4% | source · 2026-10-18 |
| LiveBench Math | 93.3% | 91.0% | source · 2026-10-18 |
| LiveBench Reasoning | 86.7% | 84% | source · 2026-10-18 |
| LMArena Agent Bash Recovery | 7.9 | -23.3 | source · 2026-10-08 |
| LMArena Creative Writing | 1438 Elo | 1483 Elo | source · 2026-11-11 |
| LMArena Instruction Following | 1473 Elo | 1465 Elo | source · 2026-11-11 |
| LMArena Long Query | 1474 Elo | 1482 Elo | source · 2026-11-11 |
| LMArena Math | 1479 Elo | 1485 Elo | source · 2026-11-11 |
| LMArena Text | 1475 Elo | 1487 Elo | source · 2026-11-11 |
| LMArena Text Factuality | 1468 Elo | 1472 Elo | source · 2026-11-11 |
| LMArena Vision | 1263 Elo | 1280 Elo | source · 2026-11-09 |
| LMArena Vision Diagrams | 1296 Elo | 1309 Elo | source · 2026-11-09 |
| LMArena Vision OCR | 1274 Elo | 1295 Elo | source · 2026-11-09 |
| LMArena WebDev | 1621 Elo | 1446 Elo | source · 2026-11-11 |
| LMArena WebDev Image-to-Web | 1610 Elo | 1480 Elo | source · 2026-11-10 |
| OTIS Mock AIME (Epoch AI) | 98.3% ± 0.6 | 95.6% ± 3.1 | source · 2026-10-08 |
| SimpleQA Verified (Epoch AI) | 42.9% ± 1.6 | 73.5% ± 1.4 | source · 2026-10-13 |
Values are as published by each evaluator, in its own units; rows from different evaluators are not on a common scale.
task evidence
How they place when the question changes
Lower ranks are better. “Best” marks the strongest option in this shortlist for that task.